fofr@fofrAI

2026-06-05 21:23·27天前

AI 摘要

fofrAI 使用 Gemini 3.5 Flash 和 Antigravity CLI 实验 AI 智能体的自主性和速度。结果：20 分钟内在 Linux CPU 上安装并运行原版 Stable Diffusion 1.5，完成推理生成图像；基于 Lora 和 SD 论文，用 10 张图片从零实现 Lora 微调器（约 1 小时 30 分，主要为 CPU 训练）；通过 modal 约 20 分钟找到 GPU、获取 Ideogram v4 权重并运行推理。该推文展示了当前长周期智能体任务的基线案例。

Today I'm experimenting with Gemini 3.5 Flash and the Antigravity CLI to see how fast and how autonomously the agents can do things.

It took 20 minutes to install and run the original CompVis Stable Diffusion 1.5 repo， get the weights， debug， run inference and generate an image on a Linux CPU. It fixed every crash and managed dependencies while making changes to run on a CPU
I gave it the original Lora and SD papers and asked it to make a lora fine tuner from first principles， with a set of 10 images. That took about 1h30， most of the time being slow training runs on the CPU， but it did optimize for multiple CPUs. It worked， it made a lora that showed a likeness and then it wanted to hill climb. I told it to think of the poor CPUs
I wanted to experiment with the new Ideogram v4 weights. It used modal to find the right class of GPU， get the code， set up the env， get the weights， run inference， that took about 20 mins in total

fofrWhere's the baseline for impressive long horizon agent tasks today? What are you seeing this week that makes you go "woah"?

智能体 Google MCP/工具大佬观点

在 X 查看原推

fofr@fofrAI · X

62导出 Markdown

2026-06-05 21:23·27天前

在 X 看原推· x.com

AI 摘要

Today I'm experimenting with Gemini 3.5 Flash and the Antigravity CLI to see how fast and how autonomously the agents can do things.

It took 20 minutes to install and run the original CompVis Stable Diffusion 1.5 repo， get the weights， debug， run inference and generate an image on a Linux CPU. It fixed every crash and managed dependencies while making changes to run on a CPU
I gave it the original Lora and SD papers and asked it to make a lora fine tuner from first principles， with a set of 10 images. That took about 1h30， most of the time being slow training runs on the CPU， but it did optimize for multiple CPUs. It worked， it made a lora that showed a likeness and then it wanted to hill climb. I told it to think of the poor CPUs